Mining thick skylines over large databases

摘要: People recently are interested in a new operator, called skyline [3], which returns the objects that not dominated by any other with regard to certain measures multi-dimensional space. Recent work on operator [3,15,8,13,2] focuses efficient computation of skylines large databases. However, such gives users only thin skylines, i.e., single objects, may be desirable some real applications. In this paper, we propose novel concept, thick skyline, recommends but also their nearby neighbors within -distance. Efficient methods developed including (1) two algorithms, Sampling-and-Pruning and Indexing-and-Estimating, find help statistics or indexes databases, (2) highly Microcluster-based algorithm for mining skyline. The method leads substantial savings provides cocise representation case high cardinalities. Our experimental performance study shows proposed both effective.